Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on pieces of source‐code identifiers (especially CamelCase or mixed‐case constant/variable names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    prototype
    -0.07
    iros
    -0.07
    (Controller
    -0.07
     ################################
    -0.06
    {{
    -0.06
    }}{{
    -0.06
    IsUnicode
    -0.06
    .ud
    -0.06
    іл
    -0.06
    وجه
    -0.06
    POSITIVE LOGITS
    uide
    0.06
     kod
    0.06
    &action
    0.06
    .yaml
    0.06
    ‬↵
    0.06
     Orc
    0.06
     acheter
    0.06
     wreak
    0.06
     inexp
    0.06
    	start
    0.06
    Act Density 0.047%

    No Known Activations